Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3254 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.7319. Min Range: -2.7319
Max Act: 2.7319. Min Act: -0.1700
Data Index: 6865692 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7319. Min Range: -2.7319
Max Act: 2.6036. Min Act: -0.1700
Data Index: 8361258 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7319. Min Range: -2.7319
Max Act: 2.5391. Min Act: -0.1700
Data Index: 8617338 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7319. Min Range: -2.7319
Max Act: 2.4581. Min Act: -0.1700
Data Index: 85969 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7319. Min Range: -2.7319
Max Act: 2.4418. Min Act: -0.1700
Data Index: 3505787 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7319. Min Range: -2.7319
Max Act: 2.4418. Min Act: -0.1700
Data Index: 7835839 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7319. Min Range: -2.7319
Max Act: 2.4256. Min Act: -0.1700
Data Index: 8464863 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7319. Min Range: -2.7319
Max Act: 2.4256. Min Act: -0.1700
Data Index: 6822139 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7319. Min Range: -2.7319
Max Act: 2.4256. Min Act: -0.1700
Data Index: 399746 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7319. Min Range: -2.7319
Max Act: 2.3929. Min Act: -0.1700
Data Index: 8506491 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7319. Min Range: -2.7319
Max Act: 2.3929. Min Act: -0.1700
Data Index: 3925673 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7319. Min Range: -2.7319
Max Act: 2.3929. Min Act: -0.1700
Data Index: 1291142 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7319. Min Range: -2.7319
Max Act: 2.3929. Min Act: -0.1700
Data Index: 7003446 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7319. Min Range: -2.7319
Max Act: 2.3929. Min Act: -0.1700
Data Index: 3276877 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7319. Min Range: -2.7319
Max Act: 2.3602. Min Act: -0.1700
Data Index: 3571082 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7319. Min Range: -2.7319
Max Act: 2.3439. Min Act: -0.1700
Data Index: 1086458 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7319. Min Range: -2.7319
Max Act: 2.3766. Min Act: -0.1700
Data Index: 4167396 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7319. Min Range: -2.7319
Max Act: 2.3602. Min Act: -0.1700
Data Index: 8502005 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7319. Min Range: -2.7319
Max Act: 2.3439. Min Act: -0.1700
Data Index: 2337544 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7319. Min Range: -2.7319
Max Act: 2.3439. Min Act: -0.1700
Data Index: 4909319 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #19